RESUMEN
OBJECTIVES: Pancreatic ductal adenocarcinoma is an intractable disease with frequent recurrence after resection and adjuvant therapy. The present study aimed to clarify whether artificial intelligence-assisted analysis of histopathological images can predict recurrence in patients with pancreatic ductal adenocarcinoma who underwent resection and adjuvant chemotherapy with tegafur/5-chloro-2,4-dihydroxypyridine/potassium oxonate. MATERIALS AND METHODS: Eighty-nine patients were enrolled in the study. Machine-learning algorithms were applied to 10-billion-scale pixel data of whole-slide histopathological images to generate key features using multiple deep autoencoders. Areas under the curve were calculated from receiver operating characteristic curves using a support vector machine with key features alone and by combining with clinical data (age and carbohydrate antigen 19-9 and carcinoembryonic antigen levels) for predicting recurrence. Supervised learning with pathological annotations was conducted to determine the significant features for predicting recurrence. RESULTS: Areas under the curves obtained were 0.73 (95% confidence interval, 0.59-0.87) by the histopathological data analysis and 0.84 (95% confidence interval, 0.73-0.94) by the combinatorial analysis of histopathological data and clinical data. Supervised learning model demonstrated that poor tumor differentiation was significantly associated with recurrence. CONCLUSIONS: Results indicate that machine learning with the integration of artificial intelligence-driven evaluation of histopathological images and conventional clinical data provides relevant prognostic information for patients with pancreatic ductal adenocarcinoma.
Asunto(s)
Carcinoma Ductal Pancreático , Neoplasias Pancreáticas , Humanos , Inteligencia Artificial , Carcinoma Ductal Pancreático/diagnóstico por imagen , Carcinoma Ductal Pancreático/tratamiento farmacológico , Carcinoma Ductal Pancreático/cirugía , Neoplasias Pancreáticas/tratamiento farmacológico , Neoplasias Pancreáticas/cirugía , Pronóstico , Aprendizaje Automático , Estudios RetrospectivosRESUMEN
Peritoneal washing cytology (CY) in patients with pancreatic cancer is mainly used for staging; however, it may also be used to evaluate the intraperitoneal status to predict a more accurate prognosis. Here, we investigated the potential of deep learning of CY specimen images for predicting the 1-year prognosis of pancreatic cancer in CY-positive patients. CY specimens from 88 patients with prognostic information were retrospectively analyzed. CY specimens scanned by the whole slide imaging device were segmented and subjected to deep learning with a Vision Transformer (ViT) and a Convolutional Neural Network (CNN). The results indicated that ViT and CNN predicted the 1-year prognosis from scanned images with accuracies of 0.8056 and 0.8009 in the area under the curve of the receiver operating characteristic curves, respectively. Patients predicted to survive 1 year or more by ViT showed significantly longer survivals by Kaplan-Meier analyses. The cell nuclei found to have a negative prognostic impact by ViT appeared to be neutrophils. Our results indicate that AI-mediated analysis of CY specimens can successfully predict the 1-year prognosis of patients with pancreatic cancer positive for CY. Intraperitoneal neutrophils may be a novel prognostic marker and therapeutic target for CY-positive patients with pancreatic cancer.
Asunto(s)
Aprendizaje Profundo , Neoplasias Pancreáticas , Humanos , Neoplasias Pancreáticas/patología , Neoplasias Pancreáticas/mortalidad , Neoplasias Pancreáticas/diagnóstico , Femenino , Masculino , Pronóstico , Persona de Mediana Edad , Anciano , Estudios Retrospectivos , Redes Neurales de la Computación , Curva ROC , Citodiagnóstico/métodos , Estimación de Kaplan-Meier , Adulto , Lavado Peritoneal , Anciano de 80 o más Años , Neutrófilos/patología , CitologíaRESUMEN
Accurate prostate cancer screening is imperative for reducing the risk of cancer death. Ultrasound imaging, although easy, tends to have low resolution and high inter-observer variability. Here, we show that our integrated machine learning approach enabled the detection of pathological high-grade cancer by the ultrasound procedure. Our study included 772 consecutive patients and 2899 prostate ultrasound images obtained at the Nippon Medical School Hospital. We applied machine learning analyses using ultrasound imaging data and clinical data to detect high-grade prostate cancer. The area under the curve (AUC) using clinical data was 0.691. On the other hand, the AUC when using clinical data and ultrasound imaging data was 0.835 (p = 0.007). Our data-driven ultrasound approach offers an efficient tool to triage patients with high-grade prostate cancers and expands the possibility of ultrasound imaging for the prostate cancer detection pathway.
Asunto(s)
Detección Precoz del Cáncer/métodos , Aprendizaje Automático , Próstata/diagnóstico por imagen , Neoplasias de la Próstata/diagnóstico por imagen , Neoplasias de la Próstata/patología , Ultrasonografía/métodos , Anciano , Área Bajo la Curva , Diagnóstico Diferencial , Humanos , Masculino , Persona de Mediana Edad , Clasificación del Tumor , Próstata/patología , Neoplasias de la Próstata/prevención & control , Triaje/métodosRESUMEN
Fluorescence and excitation spectra and fluorescence lifetimes have been measured for alpha,omega-dithienylbutadiene (DTB) and alpha,omega-dithienylethylene (DTE) in a jet-cooled He expansion and in the static vapor phase. It is shown that the emission of DTB in the static vapor phase consists of the S1(2(1)A(g)) and S2(1(1)B(u)) fluorescence, while the emission in a jet consists of solely the S1 fluorescence. The fluorescence quantum yields of DTB and DTE vapors decrease significantly with increasing excitation energy. The conformer-specific fluorescence was measured for DTB and DTE in a jet. The false S1 (2(1)A(g)) origin of the most stable conformer of DTB was observed at 25470.5 cm(-1) in a jet, which is located approximately 2800 cm(-1) below the S2 (1(1)B(u)) origin. The S1 origins of the two conformers of DTE were observed at 28648 and 28966 cm(-1) in a jet, and the S1 state of the most stable conformer is assigned as 1(1)B(u).
Asunto(s)
Butadienos/química , Etilenos/química , Teoría Cuántica , Estructura Molecular , Fotoquímica , Espectrometría de Fluorescencia , Estereoisomerismo , VolatilizaciónRESUMEN
The S0-S1 hole-burning spectra of azulene and its derivatives, 1-methyl, 2-methyl, 4-methyl, 1-cyano, and 2-cyanoazulenes, were measured under the isolated condition in order to gain an insight into the internal-conversion mechanism. The width of every 0-0 band was dependent on its transition energy and independent of the density of the S0-state vibrational levels isoenergetic to its zero level of the S1 state. On the contrary, the vibronic-band broadening of each molecule progressed in proportion to the vibrational excess energy of the S1 state. In the low-energy region, widths gradually increased, which is attributed to the normal internal conversion. A drastic increase was observed in the medium-energy region in azulene and three methyl derivatives but not in the two cyano ones. This is considered to be the onset of the relaxation process due to the conical intersection suggested by Bearpark et al. [J. Am. Chem. Soc. 1996, 118, 169]. Anomalous width behavior was found for two vibronic bands whose widths were still narrow even above the onset. One was 0 + 2659 cm(-1) band of azulene, that had been already reported by Ruth et al. [Phys. Chem. Chem. Phys. 1999, 1, 5121], and we could reproduce it by the hole-burning method. Another was 0 + 2878 cm(-1) band of 2-methylazulene. This is the vibronic selectivity in competition between the relaxation process and the normal internal conversion. The amplitude vectors of these modes were similar, including the in-plane bending of the CH bond and the stretching of the transannular bond.
RESUMEN
Deep learning algorithms have been successfully used in medical image classification. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Here we show that deep learning algorithm enables automated acquisition of explainable features from diagnostic annotation-free histopathology images. We compare the prediction accuracy of prostate cancer recurrence using our algorithm-generated features with that of diagnosis by expert pathologists using established criteria on 13,188 whole-mount pathology images consisting of over 86 billion image patches. Our method not only reveals findings established by humans but also features that have not been recognized, showing higher accuracy than human in prognostic prediction. Combining both our algorithm-generated features and human-established criteria predicts the recurrence more accurately than using either method alone. We confirm robustness of our method using external validation datasets including 2276 pathology images. This study opens up fields of machine learning analysis for discovering uncharted knowledge.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Conocimiento , Patología , Algoritmos , Automatización , Compresión de Datos , Humanos , Recurrencia Local de Neoplasia/diagnóstico por imagen , Recurrencia Local de Neoplasia/patología , Curva ROCRESUMEN
Deep learning algorithms have achieved great success in cancer image classification. However, it is imperative to understand the differences between the deep learning and human approaches. Using an explainable model, we aimed to compare the deep learning-focused regions of magnetic resonance (MR) images with cancerous locations identified by radiologists and pathologists. First, 307 prostate MR images were classified using a well-established deep neural network without locational information of cancers. Subsequently, we assessed whether the deep learning-focused regions overlapped the radiologist-identified targets. Furthermore, pathologists provided histopathological diagnoses on 896 pathological images, and we compared the deep learning-focused regions with the genuine cancer locations through 3D reconstruction of pathological images. The area under the curve (AUC) for MR images classification was sufficiently high (AUC = 0.90, 95% confidence interval 0.87-0.94). Deep learning-focused regions overlapped radiologist-identified targets by 70.5% and pathologist-identified cancer locations by 72.1%. Lymphocyte aggregation and dilated prostatic ducts were observed in non-cancerous regions focused by deep learning. Deep learning algorithms can achieve highly accurate image classification without necessarily identifying radiological targets or cancer locations. Deep learning may find clues that can help a clinical diagnosis even if the cancer is not visible.
Asunto(s)
Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética , Neoplasias de la Próstata/diagnóstico por imagen , Anciano , Humanos , MasculinoRESUMEN
BACKGROUND: Recent developments in molecular pathology and genetic/epigenetic analysis of cancer tissue have resulted in a marked increase in objective and measurable data. In comparison, the traditional morphological analysis approach to pathology diagnosis, which can connect these molecular data and clinical diagnosis, is still mostly subjective. Even though the advent and popularization of digital pathology has provided a boost to computer-aided diagnosis, some important pathological concepts still remain largely non-quantitative and their associated data measurements depend on the pathologist's sense and experience. Such features include pleomorphism and heterogeneity. METHODS AND RESULTS: In this paper, we propose a method for the objective measurement of pleomorphism and heterogeneity, using the cell-level co-occurrence matrix. Our method is based on the widely used Gray-level co-occurrence matrix (GLCM), where relations between neighboring pixel intensity levels are captured into a co-occurrence matrix, followed by the application of analysis functions such as Haralick features. In the pathological tissue image, through image processing techniques, each nucleus can be measured and each nucleus has its own measureable features like nucleus size, roundness, contour length, intra-nucleus texture data (GLCM is one of the methods). In GLCM each nucleus in the tissue image corresponds to one pixel. In this approach the most important point is how to define the neighborhood of each nucleus. We define three types of neighborhoods of a nucleus, then create the co-occurrence matrix and apply Haralick feature functions. In each image pleomorphism and heterogeneity are then determined quantitatively. For our method, one pixel corresponds to one nucleus feature, and we therefore named our method Cell Feature Level Co-occurrence Matrix (CFLCM). We tested this method for several nucleus features. CONCLUSION: CFLCM is showed as a useful quantitative method for pleomorphism and heterogeneity on histopathological image analysis.